Abstract
Noise reduction algorithms have often been evaluated using images degraded by artificially synthesised noise. The RENOIR image dataset [3] provides an alternative way for testing noise reduction algorithms on real noisy images and we propose in this paper to assess our CNN called De-Blurring Super-Resolution (DBSR) [2] to reduce the natural noise due to low light conditions in a RENOIR dataset.
Original language | English |
---|---|
DOIs | |
Publication status | Published - 1 Jan 2019 |
Externally published | Yes |
Event | IMVIP 2019: Irish Machine Vision & Image Processing - Technological University Dublin, Dublin, Ireland Duration: 28 Aug 2019 → 30 Aug 2019 |
Conference
Conference | IMVIP 2019: Irish Machine Vision & Image Processing |
---|---|
Country/Territory | Ireland |
City | Dublin |
Period | 28/08/19 → 30/08/19 |
Keywords
- Noise reduction
- RENOIR image dataset
- CNN
- De-Blurring Super-Resolution
- natural noise
- low light conditions